Convolutional Neural Networks

Project: Write an Algorithm for a Dog Identification App


In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. Sections that begin with '(IMPLEMENTATION)' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully!

Note: Once you have completed all of the code implementations, you need to finalize your work by exporting the Jupyter Notebook as an HTML document. Before exporting the notebook to html, all of the code cells need to have been run so that reviewers can see the final implementation and output. You can then export the notebook by using the menu above and navigating to File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.

In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question X' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.

Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. Markdown cells can be edited by double-clicking the cell to enter edit mode.

The rubric contains optional "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. If you decide to pursue the "Stand Out Suggestions", you should include the code in this Jupyter notebook.


Why We're Here

In this notebook, you will make the first steps towards developing an algorithm that could be used as part of a mobile or web app. At the end of this project, your code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling. The image below displays potential sample output of your finished project (... but we expect that each student's algorithm will behave differently!).

Sample Dog Output

In this real-world setting, you will need to piece together a series of models to perform different tasks; for instance, the algorithm that detects humans in an image will be different from the CNN that infers dog breed. There are many points of possible failure, and no perfect algorithm exists. Your imperfect solution will nonetheless create a fun user experience!

The Road Ahead

We break the notebook into separate steps. Feel free to use the links below to navigate the notebook.

  • Step 0: Import Datasets
  • Step 1: Detect Humans
  • Step 2: Detect Dogs
  • Step 3: Create a CNN to Classify Dog Breeds (from Scratch)
  • Step 4: Create a CNN to Classify Dog Breeds (using Transfer Learning)
  • Step 5: Write your Algorithm
  • Step 6: Test Your Algorithm

Step 0: Import Datasets

Make sure that you've downloaded the required human and dog datasets:

  • Download the dog dataset. Unzip the folder and place it in this project's home directory, at the location /dog_images.

  • Download the human dataset. Unzip the folder and place it in the home directory, at location /lfw.

Note: If you are using a Windows machine, you are encouraged to use 7zip to extract the folder.

In the code cell below, we save the file paths for both the human (LFW) dataset and dog dataset in the numpy arrays human_files and dog_files.

In [6]:
import numpy as np
from glob import glob

# load filenames for human and dog images
human_files = np.array(glob("/data/lfw/*/*"))
dog_files = np.array(glob("/data/dog_images/*/*/*"))


# print number of images in each dataset
print('There are %d total human images.' % len(human_files))
print('There are %d total dog images.' % len(dog_files))
There are 13233 total human images.
There are 8351 total dog images.

Step 1: Detect Humans

In this section, we use OpenCV's implementation of Haar feature-based cascade classifiers to detect human faces in images.

OpenCV provides many pre-trained face detectors, stored as XML files on github. We have downloaded one of these detectors and stored it in the haarcascades directory. In the next code cell, we demonstrate how to use this detector to find human faces in a sample image.

In [10]:
import cv2                
import matplotlib.pyplot as plt                        
%matplotlib inline                               

# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')

# load color (BGR) image
img = cv2.imread(human_files[0])
# convert BGR image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# find faces in image
faces = face_cascade.detectMultiScale(gray)

# print number of faces detected in the image
print('Number of faces detected:', len(faces))

# get bounding box for each detected face
for (x,y,w,h) in faces:
    # add bounding box to color image
    cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
    
# convert BGR image to RGB for plotting
cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

# display the image, along with bounding box
plt.imshow(cv_rgb)
plt.show()
Number of faces detected: 1

Before using any of the face detectors, it is standard procedure to convert the images to grayscale. The detectMultiScale function executes the classifier stored in face_cascade and takes the grayscale image as a parameter.

In the above code, faces is a numpy array of detected faces, where each row corresponds to a detected face. Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. The first two entries in the array (extracted in the above code as x and y) specify the horizontal and vertical positions of the top left corner of the bounding box. The last two entries in the array (extracted here as w and h) specify the width and height of the box.

Write a Human Face Detector

We can use this procedure to write a function that returns True if a human face is detected in an image and False otherwise. This function, aptly named face_detector, takes a string-valued file path to an image as input and appears in the code block below.

In [11]:
# returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
    img = cv2.imread(img_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray)
    return len(faces) > 0

(IMPLEMENTATION) Assess the Human Face Detector

Question 1: Use the code cell below to test the performance of the face_detector function.

  • What percentage of the first 100 images in human_files have a detected human face?
  • What percentage of the first 100 images in dog_files have a detected human face?

Ideally, we would like 100% of human images with a detected face and 0% of dog images with a detected face. You will see that our algorithm falls short of this goal, but still gives acceptable performance. We extract the file paths for the first 100 images from each of the datasets and store them in the numpy arrays human_files_short and dog_files_short.

Answer: (You can print out your results and/or write your percentages in this cell)

In [9]:
from tqdm import tqdm

human_files_short = human_files[:100]
dog_files_short = dog_files[:100]

#-#-# Do NOT modify the code above this line. #-#-#

## TODO: Test the performance of the face_detector algorithm 
## on the images in human_files_short and dog_files_short.
#HUMAN
hum_cnt=0
dog_cnt=0
for h in human_files_short:
    #Pass the image to the function which detects if it is a human face
    if face_detector(h):
        hum_cnt +=1
print(str(hum_cnt) + "%") 
#DOG
for d in dog_files_short:
    #Pass the image to the function which detects if it is a human face
    if face_detector(d):
        dog_cnt +=1
print(str(dog_cnt) + "%")
98%
17%

We suggest the face detector from OpenCV as a potential way to detect human images in your algorithm, but you are free to explore other approaches, especially approaches that make use of deep learning :). Please use the code cell below to design and test your own face detection algorithm. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.

In [5]:
### (Optional) 
### TODO: Test performance of anotherface detection algorithm.
### Feel free to use as many code cells as needed.

Step 2: Detect Dogs

In this section, we use a pre-trained model to detect dogs in images.

Obtain Pre-trained VGG-16 Model

The code cell below downloads the VGG-16 model, along with weights that have been trained on ImageNet, a very large, very popular dataset used for image classification and other vision tasks. ImageNet contains over 10 million URLs, each linking to an image containing an object from one of 1000 categories.

In [12]:
import torch
import torchvision.models as models

# define VGG16 model
VGG16 = models.vgg16(pretrained=True)

# check if CUDA is available
use_cuda = torch.cuda.is_available()

# move model to GPU if CUDA is available
if use_cuda:
    VGG16 = VGG16.cuda()
Downloading: "https://download.pytorch.org/models/vgg16-397923af.pth" to /root/.torch/models/vgg16-397923af.pth
100%|██████████| 553433881/553433881 [00:26<00:00, 20972305.41it/s]

Given an image, this pre-trained VGG-16 model returns a prediction (derived from the 1000 possible categories in ImageNet) for the object that is contained in the image.

(IMPLEMENTATION) Making Predictions with a Pre-trained Model

In the next code cell, you will write a function that accepts a path to an image (such as 'dogImages/train/001.Affenpinscher/Affenpinscher_00001.jpg') as input and returns the index corresponding to the ImageNet class that is predicted by the pre-trained VGG-16 model. The output should always be an integer between 0 and 999, inclusive.

Before writing the function, make sure that you take the time to learn how to appropriately pre-process tensors for pre-trained models in the PyTorch documentation.

In [13]:
from PIL import Image
import torchvision.transforms as transforms

def VGG16_predict(img_path):
    '''
    Use pre-trained VGG-16 model to obtain index corresponding to 
    predicted ImageNet class for image at specified path
    
    Args:
        img_path: path to an image
        
    Returns:
        Index corresponding to VGG-16 model's prediction
    '''
    
    ## TODO: Complete the function.
    ## Load and pre-process an image from the given img_path
    ## Return the *index* of the predicted class for that image
    image =Image.open(img_path).convert('RGB')
    transform =transforms.Compose([
                                   transforms.Resize(size=(244,244)),
                                   transforms.ToTensor()])
    img = transform(image)[:3,:,:].unsqueeze(0)
    if use_cuda:
        img=img.cuda()
    ret=VGG16(img)
    return torch.max(ret,1)[1].item()

# predicted class index
VGG16_predict(dog_files_short[0])
Out[13]:
243

(IMPLEMENTATION) Write a Dog Detector

While looking at the dictionary, you will notice that the categories corresponding to dogs appear in an uninterrupted sequence and correspond to dictionary keys 151-268, inclusive, to include all categories from 'Chihuahua' to 'Mexican hairless'. Thus, in order to check to see if an image is predicted to contain a dog by the pre-trained VGG-16 model, we need only check if the pre-trained model predicts an index between 151 and 268 (inclusive).

Use these ideas to complete the dog_detector function below, which returns True if a dog is detected in an image (and False if not).

In [14]:
### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
    ## TODO: Complete the function.
    det =VGG16_predict(img_path)
    return det >= 151 and det <= 268

print(dog_detector(dog_files_short[0]))
print(dog_detector(human_files_short[0]))
True
False

(IMPLEMENTATION) Assess the Dog Detector

Question 2: Use the code cell below to test the performance of your dog_detector function.

  • What percentage of the images in human_files_short have a detected dog?
  • What percentage of the images in dog_files_short have a detected dog?

Answer:

In [15]:
### TODO: Test the performance of the dog_detector function
### on the images in human_files_short and dog_files_short.
def dog_detector_test(files):
    det_cnt = 0;
    total_cnt = len(files)
    for file in files:
        det_cnt += dog_detector(file)
    return det_cnt, total_cnt
 
print("Dogs detected in human files: {} / {}".format(dog_detector_test(human_files_short)[0],
                                                     dog_detector_test(human_files_short)[1]))
print("Dogs detected in dog files: {} / {}".format(dog_detector_test(dog_files_short)[0],
                                                     dog_detector_test(dog_files_short)[1]))
Dogs detected in human files: 0 / 100
Dogs detected in dog files: 99 / 100

We suggest VGG-16 as a potential network to detect dog images in your algorithm, but you are free to explore other pre-trained networks (such as Inception-v3, ResNet-50, etc). Please use the code cell below to test other pre-trained PyTorch models. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.

In [16]:
### (Optional) 
### TODO: Report the performance of another pre-trained network.
### Feel free to use as many code cells as needed.

Step 3: Create a CNN to Classify Dog Breeds (from Scratch)

Now that we have functions for detecting humans and dogs in images, we need a way to predict breed from images. In this step, you will create a CNN that classifies dog breeds. You must create your CNN from scratch (so, you can't use transfer learning yet!), and you must attain a test accuracy of at least 10%. In Step 4 of this notebook, you will have the opportunity to use transfer learning to create a CNN that attains greatly improved accuracy.

We mention that the task of assigning breed to dogs from images is considered exceptionally challenging. To see why, consider that even a human would have trouble distinguishing between a Brittany and a Welsh Springer Spaniel.

Brittany Welsh Springer Spaniel

It is not difficult to find other dog breed pairs with minimal inter-class variation (for instance, Curly-Coated Retrievers and American Water Spaniels).

Curly-Coated Retriever American Water Spaniel

Likewise, recall that labradors come in yellow, chocolate, and black. Your vision-based algorithm will have to conquer this high intra-class variation to determine how to classify all of these different shades as the same breed.

Yellow Labrador Chocolate Labrador Black Labrador

We also mention that random chance presents an exceptionally low bar: setting aside the fact that the classes are slightly imabalanced, a random guess will provide a correct answer roughly 1 in 133 times, which corresponds to an accuracy of less than 1%.

Remember that the practice is far ahead of the theory in deep learning. Experiment with many different architectures, and trust your intuition. And, of course, have fun!

(IMPLEMENTATION) Specify Data Loaders for the Dog Dataset

Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dog_images/train, dog_images/valid, and dog_images/test, respectively). You may find this documentation on custom datasets to be a useful resource. If you are interested in augmenting your training and/or validation data, check out the wide variety of transforms!

In [17]:
import os
import random
import requests
import time
import ast
import numpy as np
from glob import glob
import cv2                
from tqdm import tqdm
from PIL import Image, ImageFile 

import torch
import torchvision
from torchvision import datasets
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision.models as models

import matplotlib.pyplot as plt                        
%matplotlib inline

ImageFile.LOAD_TRUNCATED_IMAGES = True

# check if CUDA is available
use_cuda = torch.cuda.is_available()
In [18]:
### TODO: Write data loaders for training, validation, and test sets
## Specify appropriate transforms, and batch_sizes


# how many samples per batch to load
batch_size = 16

# number of subprocesses to use for data loading
num_workers = 2

# convert data to a normalized torch.FloatTensor
transform = transforms.Compose([transforms.Resize(size=224),
                                transforms.CenterCrop((224,224)),
                                transforms.RandomHorizontalFlip(), # randomly flip and rotate
                                transforms.RandomRotation(10),
                                transforms.ToTensor(),
                                transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])

# define training, test and validation data directories
data_dir = '/data/dog_images/'

image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x), transform)
                  for x in ['train', 'valid', 'test']}
loaders_scratch = {
    x: torch.utils.data.DataLoader(image_datasets[x], shuffle=True, batch_size=batch_size, num_workers=num_workers)
    for x in ['train', 'valid', 'test']}

Question 3: Describe your chosen procedure for preprocessing the data.

  • How does your code resize the images (by cropping, stretching, etc)? What size did you pick for the input tensor, and why?
  • Did you decide to augment the dataset? If so, how (through translations, flips, rotations, etc)? If not, why not?

Train dataset

In [19]:
train_names = image_datasets['train'].classes
train_classes = len(train_names)

print("No of classes:", train_classes)
print("\nClass name: \n\n", train_names)
No of classes: 133

Class name: 

 ['001.Affenpinscher', '002.Afghan_hound', '003.Airedale_terrier', '004.Akita', '005.Alaskan_malamute', '006.American_eskimo_dog', '007.American_foxhound', '008.American_staffordshire_terrier', '009.American_water_spaniel', '010.Anatolian_shepherd_dog', '011.Australian_cattle_dog', '012.Australian_shepherd', '013.Australian_terrier', '014.Basenji', '015.Basset_hound', '016.Beagle', '017.Bearded_collie', '018.Beauceron', '019.Bedlington_terrier', '020.Belgian_malinois', '021.Belgian_sheepdog', '022.Belgian_tervuren', '023.Bernese_mountain_dog', '024.Bichon_frise', '025.Black_and_tan_coonhound', '026.Black_russian_terrier', '027.Bloodhound', '028.Bluetick_coonhound', '029.Border_collie', '030.Border_terrier', '031.Borzoi', '032.Boston_terrier', '033.Bouvier_des_flandres', '034.Boxer', '035.Boykin_spaniel', '036.Briard', '037.Brittany', '038.Brussels_griffon', '039.Bull_terrier', '040.Bulldog', '041.Bullmastiff', '042.Cairn_terrier', '043.Canaan_dog', '044.Cane_corso', '045.Cardigan_welsh_corgi', '046.Cavalier_king_charles_spaniel', '047.Chesapeake_bay_retriever', '048.Chihuahua', '049.Chinese_crested', '050.Chinese_shar-pei', '051.Chow_chow', '052.Clumber_spaniel', '053.Cocker_spaniel', '054.Collie', '055.Curly-coated_retriever', '056.Dachshund', '057.Dalmatian', '058.Dandie_dinmont_terrier', '059.Doberman_pinscher', '060.Dogue_de_bordeaux', '061.English_cocker_spaniel', '062.English_setter', '063.English_springer_spaniel', '064.English_toy_spaniel', '065.Entlebucher_mountain_dog', '066.Field_spaniel', '067.Finnish_spitz', '068.Flat-coated_retriever', '069.French_bulldog', '070.German_pinscher', '071.German_shepherd_dog', '072.German_shorthaired_pointer', '073.German_wirehaired_pointer', '074.Giant_schnauzer', '075.Glen_of_imaal_terrier', '076.Golden_retriever', '077.Gordon_setter', '078.Great_dane', '079.Great_pyrenees', '080.Greater_swiss_mountain_dog', '081.Greyhound', '082.Havanese', '083.Ibizan_hound', '084.Icelandic_sheepdog', '085.Irish_red_and_white_setter', '086.Irish_setter', '087.Irish_terrier', '088.Irish_water_spaniel', '089.Irish_wolfhound', '090.Italian_greyhound', '091.Japanese_chin', '092.Keeshond', '093.Kerry_blue_terrier', '094.Komondor', '095.Kuvasz', '096.Labrador_retriever', '097.Lakeland_terrier', '098.Leonberger', '099.Lhasa_apso', '100.Lowchen', '101.Maltese', '102.Manchester_terrier', '103.Mastiff', '104.Miniature_schnauzer', '105.Neapolitan_mastiff', '106.Newfoundland', '107.Norfolk_terrier', '108.Norwegian_buhund', '109.Norwegian_elkhound', '110.Norwegian_lundehund', '111.Norwich_terrier', '112.Nova_scotia_duck_tolling_retriever', '113.Old_english_sheepdog', '114.Otterhound', '115.Papillon', '116.Parson_russell_terrier', '117.Pekingese', '118.Pembroke_welsh_corgi', '119.Petit_basset_griffon_vendeen', '120.Pharaoh_hound', '121.Plott', '122.Pointer', '123.Pomeranian', '124.Poodle', '125.Portuguese_water_dog', '126.Saint_bernard', '127.Silky_terrier', '128.Smooth_fox_terrier', '129.Tibetan_mastiff', '130.Welsh_springer_spaniel', '131.Wirehaired_pointing_griffon', '132.Xoloitzcuintli', '133.Yorkshire_terrier']

Training Dataset

In [20]:
# import torchvision
# Get a batch of training data
inputs, classes = next(iter(loaders_scratch['train']))

for image, label in zip(inputs, classes): 
    image = image.to("cpu").clone().detach()
    image = image.numpy().squeeze()
    image = image.transpose(1,2,0)
    image = image * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
    image = image.clip(0, 1)
     
    fig = plt.figure(figsize=(12,3))
    plt.imshow(image)
    plt.title(train_names[label])

valid dataset

In [21]:
valid_names = image_datasets['train'].classes
valid_classes = len(valid_names)

print("No of valid classes:", valid_classes)
print("\n valid Class name: \n\n", valid_names)
No of valid classes: 133

 valid Class name: 

 ['001.Affenpinscher', '002.Afghan_hound', '003.Airedale_terrier', '004.Akita', '005.Alaskan_malamute', '006.American_eskimo_dog', '007.American_foxhound', '008.American_staffordshire_terrier', '009.American_water_spaniel', '010.Anatolian_shepherd_dog', '011.Australian_cattle_dog', '012.Australian_shepherd', '013.Australian_terrier', '014.Basenji', '015.Basset_hound', '016.Beagle', '017.Bearded_collie', '018.Beauceron', '019.Bedlington_terrier', '020.Belgian_malinois', '021.Belgian_sheepdog', '022.Belgian_tervuren', '023.Bernese_mountain_dog', '024.Bichon_frise', '025.Black_and_tan_coonhound', '026.Black_russian_terrier', '027.Bloodhound', '028.Bluetick_coonhound', '029.Border_collie', '030.Border_terrier', '031.Borzoi', '032.Boston_terrier', '033.Bouvier_des_flandres', '034.Boxer', '035.Boykin_spaniel', '036.Briard', '037.Brittany', '038.Brussels_griffon', '039.Bull_terrier', '040.Bulldog', '041.Bullmastiff', '042.Cairn_terrier', '043.Canaan_dog', '044.Cane_corso', '045.Cardigan_welsh_corgi', '046.Cavalier_king_charles_spaniel', '047.Chesapeake_bay_retriever', '048.Chihuahua', '049.Chinese_crested', '050.Chinese_shar-pei', '051.Chow_chow', '052.Clumber_spaniel', '053.Cocker_spaniel', '054.Collie', '055.Curly-coated_retriever', '056.Dachshund', '057.Dalmatian', '058.Dandie_dinmont_terrier', '059.Doberman_pinscher', '060.Dogue_de_bordeaux', '061.English_cocker_spaniel', '062.English_setter', '063.English_springer_spaniel', '064.English_toy_spaniel', '065.Entlebucher_mountain_dog', '066.Field_spaniel', '067.Finnish_spitz', '068.Flat-coated_retriever', '069.French_bulldog', '070.German_pinscher', '071.German_shepherd_dog', '072.German_shorthaired_pointer', '073.German_wirehaired_pointer', '074.Giant_schnauzer', '075.Glen_of_imaal_terrier', '076.Golden_retriever', '077.Gordon_setter', '078.Great_dane', '079.Great_pyrenees', '080.Greater_swiss_mountain_dog', '081.Greyhound', '082.Havanese', '083.Ibizan_hound', '084.Icelandic_sheepdog', '085.Irish_red_and_white_setter', '086.Irish_setter', '087.Irish_terrier', '088.Irish_water_spaniel', '089.Irish_wolfhound', '090.Italian_greyhound', '091.Japanese_chin', '092.Keeshond', '093.Kerry_blue_terrier', '094.Komondor', '095.Kuvasz', '096.Labrador_retriever', '097.Lakeland_terrier', '098.Leonberger', '099.Lhasa_apso', '100.Lowchen', '101.Maltese', '102.Manchester_terrier', '103.Mastiff', '104.Miniature_schnauzer', '105.Neapolitan_mastiff', '106.Newfoundland', '107.Norfolk_terrier', '108.Norwegian_buhund', '109.Norwegian_elkhound', '110.Norwegian_lundehund', '111.Norwich_terrier', '112.Nova_scotia_duck_tolling_retriever', '113.Old_english_sheepdog', '114.Otterhound', '115.Papillon', '116.Parson_russell_terrier', '117.Pekingese', '118.Pembroke_welsh_corgi', '119.Petit_basset_griffon_vendeen', '120.Pharaoh_hound', '121.Plott', '122.Pointer', '123.Pomeranian', '124.Poodle', '125.Portuguese_water_dog', '126.Saint_bernard', '127.Silky_terrier', '128.Smooth_fox_terrier', '129.Tibetan_mastiff', '130.Welsh_springer_spaniel', '131.Wirehaired_pointing_griffon', '132.Xoloitzcuintli', '133.Yorkshire_terrier']
In [22]:
# import torchvision
# Get a batch of validation data
inputs, classes = next(iter(loaders_scratch['valid']))

for image, label in zip(inputs, classes): 
    image = image.to("cpu").clone().detach()
    image = image.numpy().squeeze()
    image = image.transpose(1,2,0)
    image = image * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
    image = image.clip(0, 1)
     
    fig = plt.figure(figsize=(12,3))
    plt.imshow(image)
    plt.title(valid_names[label])

Test dataset

In [23]:
test_dataset=image_datasets["valid"]

print("no of classes",len(test_dataset))
print("names of the dataset",test_dataset.classes)
no of classes 835
names of the dataset ['001.Affenpinscher', '002.Afghan_hound', '003.Airedale_terrier', '004.Akita', '005.Alaskan_malamute', '006.American_eskimo_dog', '007.American_foxhound', '008.American_staffordshire_terrier', '009.American_water_spaniel', '010.Anatolian_shepherd_dog', '011.Australian_cattle_dog', '012.Australian_shepherd', '013.Australian_terrier', '014.Basenji', '015.Basset_hound', '016.Beagle', '017.Bearded_collie', '018.Beauceron', '019.Bedlington_terrier', '020.Belgian_malinois', '021.Belgian_sheepdog', '022.Belgian_tervuren', '023.Bernese_mountain_dog', '024.Bichon_frise', '025.Black_and_tan_coonhound', '026.Black_russian_terrier', '027.Bloodhound', '028.Bluetick_coonhound', '029.Border_collie', '030.Border_terrier', '031.Borzoi', '032.Boston_terrier', '033.Bouvier_des_flandres', '034.Boxer', '035.Boykin_spaniel', '036.Briard', '037.Brittany', '038.Brussels_griffon', '039.Bull_terrier', '040.Bulldog', '041.Bullmastiff', '042.Cairn_terrier', '043.Canaan_dog', '044.Cane_corso', '045.Cardigan_welsh_corgi', '046.Cavalier_king_charles_spaniel', '047.Chesapeake_bay_retriever', '048.Chihuahua', '049.Chinese_crested', '050.Chinese_shar-pei', '051.Chow_chow', '052.Clumber_spaniel', '053.Cocker_spaniel', '054.Collie', '055.Curly-coated_retriever', '056.Dachshund', '057.Dalmatian', '058.Dandie_dinmont_terrier', '059.Doberman_pinscher', '060.Dogue_de_bordeaux', '061.English_cocker_spaniel', '062.English_setter', '063.English_springer_spaniel', '064.English_toy_spaniel', '065.Entlebucher_mountain_dog', '066.Field_spaniel', '067.Finnish_spitz', '068.Flat-coated_retriever', '069.French_bulldog', '070.German_pinscher', '071.German_shepherd_dog', '072.German_shorthaired_pointer', '073.German_wirehaired_pointer', '074.Giant_schnauzer', '075.Glen_of_imaal_terrier', '076.Golden_retriever', '077.Gordon_setter', '078.Great_dane', '079.Great_pyrenees', '080.Greater_swiss_mountain_dog', '081.Greyhound', '082.Havanese', '083.Ibizan_hound', '084.Icelandic_sheepdog', '085.Irish_red_and_white_setter', '086.Irish_setter', '087.Irish_terrier', '088.Irish_water_spaniel', '089.Irish_wolfhound', '090.Italian_greyhound', '091.Japanese_chin', '092.Keeshond', '093.Kerry_blue_terrier', '094.Komondor', '095.Kuvasz', '096.Labrador_retriever', '097.Lakeland_terrier', '098.Leonberger', '099.Lhasa_apso', '100.Lowchen', '101.Maltese', '102.Manchester_terrier', '103.Mastiff', '104.Miniature_schnauzer', '105.Neapolitan_mastiff', '106.Newfoundland', '107.Norfolk_terrier', '108.Norwegian_buhund', '109.Norwegian_elkhound', '110.Norwegian_lundehund', '111.Norwich_terrier', '112.Nova_scotia_duck_tolling_retriever', '113.Old_english_sheepdog', '114.Otterhound', '115.Papillon', '116.Parson_russell_terrier', '117.Pekingese', '118.Pembroke_welsh_corgi', '119.Petit_basset_griffon_vendeen', '120.Pharaoh_hound', '121.Plott', '122.Pointer', '123.Pomeranian', '124.Poodle', '125.Portuguese_water_dog', '126.Saint_bernard', '127.Silky_terrier', '128.Smooth_fox_terrier', '129.Tibetan_mastiff', '130.Welsh_springer_spaniel', '131.Wirehaired_pointing_griffon', '132.Xoloitzcuintli', '133.Yorkshire_terrier']
In [24]:
# import torchvision
# Get a batch of test data
inputs, classes = next(iter(loaders_scratch['test']))

for image, label in zip(inputs, classes): 
    image = image.to("cpu").clone().detach()
    image = image.numpy().squeeze()
    image = image.transpose(1,2,0)
    image = image * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
    image = image.clip(0, 1)
     
    fig = plt.figure(figsize=(12,3))
    plt.imshow(image)
    plt.title(test_dataset.classes[label])

Answer: Train,test and validation dataset was loaded and dataloaders was created for each of these sets of data.

Image was resized to 224, center cropped and added some simple data augmentation by randomly flipping and rotating the given image data.

The problem iteratively approached based on previous examples.

We are working with (224, 224, 3) images

Most of the pretrained models require the input to be 224x224 images. Also, we'll need to match the normalization used when the models were trained. Each color channel was normalized separately, the means are [0.485, 0.456, 0.406] and the standard deviations are [0.229, 0.224, 0.225].

(IMPLEMENTATION) Model Architecture

Create a CNN to classify dog breed. Use the template in the code cell below.

In [25]:
# define the CNN architecture
class Net(nn.Module):
    ### TODO: choose an architecture, and complete the class
    def __init__(self):
        super(Net, self).__init__()
        ## Define layers of a CNN
        
#         self.conv1 = nn.Sequential(
#             nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1),
#             nn.BatchNorm2d(16),
#             nn.ReLU())
#         self.conv2 = nn.Sequential(
#             nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1),
#             nn.BatchNorm2d(32),
#             nn.ReLU())
        self.conv1 = nn.Conv2d(3, 16, 3, padding=1)
        # convolutional layer (sees 16x16x16 tensor)
        self.conv2 = nn.Conv2d(16, 32, 3, padding=1)
        
        # convolutional layer (sees 8x8x32 tensor)
        self.conv3 = nn.Conv2d(32, 64, 3, padding=1)

        # max pooling layer
        self.pool = nn.MaxPool2d(2, 2)
        # linear layer (64 * 28 * 28 -> 500)
        self.fc1 = nn.Linear(64 * 28 * 28, 500)
        # linear layer (500 -> 133)
        self.fc2 = nn.Linear(500, 133)
        # dropout layer (p=0.25)
        self.dropout = nn.Dropout(0.25)
        self.batch_norm = nn.BatchNorm1d(num_features=500)
    
    def forward(self, x):
        ## Define forward behavior
        x = self.pool(F.relu(self.conv1(x)))
        
        # add dropout layer
        x = self.dropout(x)
        
        x = self.pool(F.relu(self.conv2(x)))
        
        # add dropout layer
        x = self.dropout(x)
        
        x = self.pool(F.relu(self.conv3(x)))

        # add dropout layer
        x = self.dropout(x)
        
        # flatten image input
        # 64 * 28 * 28         
#         x = x.view(-1, 64 * 28 * 28)
        x = x.view(x.size(0), -1)
        
        # add 1st hidden layer, with relu activation function
        x = F.relu(self.batch_norm(self.fc1(x)))
        
        # add dropout layer
        x = self.dropout(x)
        
        # add 2nd hidden layer, with relu activation function
        x = self.fc2(x)
        return x

#-#-# You so NOT have to modify the code below this line. #-#-#

# instantiate the CNN
model_scratch = Net()
print(model_scratch)

# move tensors to GPU if CUDA is available
if use_cuda:
    model_scratch.cuda()
Net(
  (conv1): Conv2d(3, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv2): Conv2d(16, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv3): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (fc1): Linear(in_features=50176, out_features=500, bias=True)
  (fc2): Linear(in_features=500, out_features=133, bias=True)
  (dropout): Dropout(p=0.25)
  (batch_norm): BatchNorm1d(500, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
)

Question 4: Outline the steps you took to get to your final CNN architecture and your reasoning at each step.

Answer:

Input shape of of the first layer is (224, 224, 3) and last layer should output 133 classes.

Convolution layer was added and Maxpooling layers(reduce the x-y size of an input, keeping only the most active pixels from the previous layer) as well as the usual Linear + Dropout layers to avoid overfitting and produce a 133-dim output.

MaxPooling2D seems to be a common choice to downsample in these type of classification problems and that is why I chose it.

The more convolutional layers we include, the more complex patterns in color and shape a model can detect.

The first layer in my CNN is a convolutional layer that takes (224, 224, 3) inpute shape.

I'd like my new layer to have 16 filters, each with a height and width of 3. When performing the convolution, I'd like the filter to jump 1 pixel at a time.

_nn.Conv2d(in_channels, out_channels, kernelsize, stride=1, padding=0)

I want this layer to have the same width and height as the input layer, so I will pad accordingly; Then, to construct this convolutional layer, I would use the following line of code: self.conv2 = nn.Conv2d(3, 32, 3, padding=1)

I am adding a pool layer that takes in a kernel_size and a stride after every convolution layer. This will down-sample the input's x-y dimensions, by a factor of 2:

self.pool = nn.MaxPool2d(2,2)

(IMPLEMENTATION) Specify Loss Function and Optimizer

Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_scratch, and the optimizer as optimizer_scratch below.

In [26]:
### TODO: select loss function
criterion_scratch = nn.CrossEntropyLoss()

### TODO: select optimizer
optimizer_scratch = optim.SGD(model_scratch.parameters(), lr = 0.03)

(IMPLEMENTATION) Train and Validate the Model

Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_scratch.pt'.

In [27]:
def train(n_epochs, loaders, model, optimizer, criterion, use_cuda, save_path):
    """returns trained model"""
    # initialize tracker for minimum validation loss
    
    valid_loss_min = 3.877533 #np.Inf
    
    if os.path.exists(save_path):
        model.load_state_dict(torch.load(save_path))
    
    for epoch in range(1, n_epochs+1):
        # variables for training and validation loss
        train_loss = 0.0
        valid_loss = 0.0
        
        ###
        # TRAININING
        ###
        model.train()
        for data, target in loaders['train']:
            # move to GPU
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            
            # clear the gradients of all optimized variables
            optimizer.zero_grad()
            # forward pass: compute predicted outputs by passing inputs to the model
            output = model(data)
            # calculate the batch loss
            loss = criterion(output, target)
            # backward pass: compute gradient of the loss with respect to model parameters
            loss.backward()
            # perform a single optimization step (parameter update)
            optimizer.step()
            # update training loss
            train_loss += loss.item()*data.size(0)
            
        ######################    
        # VALIDATE 
        ######################
        model.eval()
        for data, target in loaders['valid']:
            # move to GPU
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            ## update the average validation loss
    
            # forward pass: compute predicted outputs by passing inputs to the model
            output = model(data)
            # calculate the batch loss
            loss = criterion(output, target)
            # update average validation loss 
            valid_loss += loss.item()*data.size(0)
            
        # calculate average losses
        train_loss = train_loss/len(loaders['train'].dataset)
        valid_loss = valid_loss/len(loaders['valid'].dataset)
        
        # print training/validation statistics 
        print('Epoch: {} \tTraining Loss: {:.6f} \t Validation Loss: {:.6f}'.format(
            epoch, 
            train_loss,
            valid_loss
            ))
        
        ## TODO: save the model if validation loss has decreased
        # save model if validation loss has decreased
        if valid_loss <= valid_loss_min:
            print('Validation loss decreased ({:.6f} --> {:.6f}).  Saving model ...'.format(
            valid_loss_min,
            valid_loss))
            torch.save(model.state_dict(), save_path)
            valid_loss_min = valid_loss
    # return trained model
    return model
In [30]:
# Train the model
model_scratch = train(10, loaders_scratch, model_scratch, optimizer_scratch, 
                      criterion_scratch, use_cuda, 'model_scratch.pt')
Epoch: 1 	Training Loss: 2.838017 	Validation Loss: 3.936628
Epoch: 2 	Training Loss: 2.649312 	Validation Loss: 3.976453
Epoch: 3 	Training Loss: 2.432000 	Validation Loss: 3.875014
Validation loss decreased (3.877533 --> 3.875014).  Saving model ...
Epoch: 4 	Training Loss: 2.235138 	Validation Loss: 3.834259
Validation loss decreased (3.875014 --> 3.834259).  Saving model ...
Epoch: 5 	Training Loss: 2.042943 	Validation Loss: 4.127688
Epoch: 6 	Training Loss: 1.866818 	Validation Loss: 3.960232
Epoch: 7 	Training Loss: 1.638341 	Validation Loss: 3.878669
Epoch: 8 	Training Loss: 1.473986 	Validation Loss: 4.058921
Epoch: 9 	Training Loss: 1.321986 	Validation Loss: 4.245104
Epoch: 10 	Training Loss: 1.184208 	Validation Loss: 4.091607

(IMPLEMENTATION) Test the Model

Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 10%.

In [32]:
def test(loaders, model, criterion, use_cuda):

    # monitor test loss and accuracy
    test_loss = 0.
    correct = 0.
    total = 0.

    model.eval()
    for batch_idx, (data, target) in enumerate(loaders['test']):
        # move to GPU
        if use_cuda:
            data, target = data.cuda(), target.cuda()
        # forward pass: compute predicted outputs by passing inputs to the model
        output = model(data)
        # calculate the loss
        loss = criterion(output, target)
        
        # update average test loss 
        test_loss += loss.item()*data.size(0)
        # convert output probabilities to predicted class
        pred = output.data.max(1, keepdim=True)[1]
        # compare predictions to true label
        correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
        total += data.size(0)
        # print testing statistics 
            
    # calculate average loss
    test_loss = test_loss/len(loaders['test'].dataset)
        
    # print test statistics 
    print('Testing Loss Average: {:.6f} '.format(test_loss))
    
    print('\nTest Accuracy: %2d%% (%2d/%2d)' % (
        100. * correct / total, correct, total))
In [33]:
# call test function    
test(loaders_scratch, model_scratch, criterion_scratch, use_cuda)
Testing Loss Average: 4.100780 

Test Accuracy: 12% (107/836)

Step 4: Create a CNN to Classify Dog Breeds (using Transfer Learning)

You will now use transfer learning to create a CNN that can identify dog breed from images. Your CNN must attain at least 60% accuracy on the test set.

(IMPLEMENTATION) Specify Data Loaders for the Dog Dataset

Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dogImages/train, dogImages/valid, and dogImages/test, respectively).

If you like, you are welcome to use the same data loaders from the previous step, when you created a CNN from scratch.

In [34]:
## TODO: Specify data loaders
loaders_transfer = loaders_scratch
print(loaders_transfer)
{'train': <torch.utils.data.dataloader.DataLoader object at 0x7f56aa9eb9e8>, 'valid': <torch.utils.data.dataloader.DataLoader object at 0x7f56aa9ebba8>, 'test': <torch.utils.data.dataloader.DataLoader object at 0x7f56aa9ebcf8>}

(IMPLEMENTATION) Model Architecture

Use transfer learning to create a CNN to classify dog breed. Use the code cell below, and save your initialized model as the variable model_transfer.

In [36]:
import torchvision.models as models
import torch.nn as nn

## TODO: Specify model architecture 
model_transfer = models.resnet50(pretrained=True)

if use_cuda:
    model_transfer = model_transfer.cuda()
In [37]:
model_transfer
Out[37]:
ResNet(
  (conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
  (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (relu): ReLU(inplace)
  (maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
  (layer1): Sequential(
    (0): Bottleneck(
      (conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (downsample): Sequential(
        (0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): Bottleneck(
      (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
    (2): Bottleneck(
      (conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
  )
  (layer2): Sequential(
    (0): Bottleneck(
      (conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (downsample): Sequential(
        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): Bottleneck(
      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
    (2): Bottleneck(
      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
    (3): Bottleneck(
      (conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
  )
  (layer3): Sequential(
    (0): Bottleneck(
      (conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (downsample): Sequential(
        (0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): Bottleneck(
      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
    (2): Bottleneck(
      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
    (3): Bottleneck(
      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
    (4): Bottleneck(
      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
    (5): Bottleneck(
      (conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
  )
  (layer4): Sequential(
    (0): Bottleneck(
      (conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (downsample): Sequential(
        (0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)
        (1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): Bottleneck(
      (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
    (2): Bottleneck(
      (conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)
      (bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
    )
  )
  (avgpool): AvgPool2d(kernel_size=7, stride=1, padding=0)
  (fc): Linear(in_features=2048, out_features=1000, bias=True)
)

Question 5: Outline the steps you took to get to your final CNN architecture and your reasoning at each step. Describe why you think the architecture is suitable for the current problem.

Answer:

Pre-trained networks are effecient to solve challenging problems.

Once trained, these models work very well as feature detectors for images they weren't trained on.In this example we are building a dog classifier which is an image classification problem

I have used resnet50 trained on ImageNet.

The classifier part of the model is a single fully-connected layer:

(fc): Linear(in_features=2048, out_features=1000, bias=True)

This layer was trained on the ImageNet dataset, so it won't work for the dog classification specific problem.we need to replace it with the classifier (133 classes), but the features will work perfectly on their own.

In [40]:
#Freeze parameters so we don't backprop through them
for param in model_transfer.parameters():
    param.requires_grad = False
# Replace the last fully connected layer with a Linnear layer with 133 out features
model_transfer.fc = nn.Linear(2048, 133)
if use_cuda:
    model_transfer = model_transfer.cuda()

(IMPLEMENTATION) Specify Loss Function and Optimizer

Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_transfer, and the optimizer as optimizer_transfer below.

In [41]:
criterion_transfer = nn.CrossEntropyLoss()
optimizer_transfer = optim.Adam(model_transfer.fc.parameters(), lr=0.001)

(IMPLEMENTATION) Train and Validate the Model

Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_transfer.pt'.

In [42]:
# train the model
model_transfer =  train(12, loaders_transfer, model_transfer, optimizer_transfer, criterion_transfer, use_cuda, 
                        'model_transfer.pt')
# load the model that got the best validation accuracy (uncomment the line below)
model_transfer.load_state_dict(torch.load('model_transfer.pt'))
Epoch: 1 	Training Loss: 2.019774 	Validation Loss: 0.807084
Validation loss decreased (3.877533 --> 0.807084).  Saving model ...
Epoch: 2 	Training Loss: 0.773756 	Validation Loss: 0.670331
Validation loss decreased (0.807084 --> 0.670331).  Saving model ...
Epoch: 3 	Training Loss: 0.612370 	Validation Loss: 0.594446
Validation loss decreased (0.670331 --> 0.594446).  Saving model ...
Epoch: 4 	Training Loss: 0.547008 	Validation Loss: 0.634747
Epoch: 5 	Training Loss: 0.504146 	Validation Loss: 0.690993
Epoch: 6 	Training Loss: 0.463687 	Validation Loss: 0.687435
Epoch: 7 	Training Loss: 0.401669 	Validation Loss: 0.561719
Validation loss decreased (0.594446 --> 0.561719).  Saving model ...
Epoch: 8 	Training Loss: 0.414961 	Validation Loss: 0.691268
Epoch: 9 	Training Loss: 0.381896 	Validation Loss: 0.659840
Epoch: 10 	Training Loss: 0.364524 	Validation Loss: 0.600265
Epoch: 11 	Training Loss: 0.355407 	Validation Loss: 0.667310
Epoch: 12 	Training Loss: 0.336898 	Validation Loss: 0.542593
Validation loss decreased (0.561719 --> 0.542593).  Saving model ...

(IMPLEMENTATION) Test the Model

Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 60%.

In [43]:
test(loaders_transfer, model_transfer, criterion_transfer, use_cuda)
Testing Loss Average: 0.624038 

Test Accuracy: 82% (692/836)

(IMPLEMENTATION) Predict Dog Breed with the Model

Write a function that takes an image path as input and returns the dog breed (Affenpinscher, Afghan hound, etc) that is predicted by your model.

In [53]:
# list of class names by index, i.e. a name can be accessed like class_names[0]
class_names = [item[4:].replace("_", " ") for item in loaders_transfer['train'].dataset.classes]
loaders_transfer['train'].dataset.classes[:10]
Out[53]:
['001.Affenpinscher',
 '002.Afghan_hound',
 '003.Airedale_terrier',
 '004.Akita',
 '005.Alaskan_malamute',
 '006.American_eskimo_dog',
 '007.American_foxhound',
 '008.American_staffordshire_terrier',
 '009.American_water_spaniel',
 '010.Anatolian_shepherd_dog']
In [52]:
class_names[:10]
Out[52]:
['Affenpinscher',
 'Afghan hound',
 'Airedale terrier',
 'Akita',
 'Alaskan malamute',
 'American eskimo dog',
 'American foxhound',
 'American staffordshire terrier',
 'American water spaniel',
 'Anatolian shepherd dog']
In [60]:
def image_to_tensor(img_path):
    img = Image.open(img_path).convert('RGB')
    transformations = transforms.Compose([transforms.Resize(size=224),
                                          transforms.CenterCrop((224,224)),
                                         transforms.ToTensor(),
                                         transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                                              std=[0.229, 0.224, 0.225])])
    image_tensor = transformations(img)[:3,:,:].unsqueeze(0)
    return image_tensor
In [61]:
def predict_breed_transfer(img_path):
    # load the image and return the predicted breed
    image_tensor = image_to_tensor(img_path)

    # move model inputs to cuda, if GPU available
    if use_cuda:
        image_tensor = image_tensor.cuda()

    # get sample outputs
    output = model_transfer(image_tensor)
    # convert output probabilities to predicted class
    _, preds_tensor = torch.max(output, 1)
    pred = np.squeeze(preds_tensor.numpy()) if not use_cuda else np.squeeze(preds_tensor.cpu().numpy())
    
    return class_names[pred]
In [62]:
def display_image(img_path, title="Title"):
    image = Image.open(img_path)
    plt.title(title)
    plt.imshow(image)
    plt.show()
In [63]:
import random

# Try out the function
for image in random.sample(list(human_files_short), 4): 
    predicted_breed = predict_breed_transfer(image)
    display_image(image, title=f"Predicted:{predicted_breed}")

Step 5: Write your Algorithm

Write an algorithm that accepts a file path to an image and first determines whether the image contains a human, dog, or neither. Then,

  • if a dog is detected in the image, return the predicted breed.
  • if a human is detected in the image, return the resembling dog breed.
  • if neither is detected in the image, provide output that indicates an error.

You are welcome to write your own functions for detecting humans and dogs in images, but feel free to use the face_detector and human_detector functions developed above. You are required to use your CNN from Step 4 to predict dog breed.

Some sample output for our algorithm is provided below, but feel free to design your own user experience!

Sample Human Output

(IMPLEMENTATION) Write your Algorithm

In [75]:
haar_face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')
img = cv2.imread(human_files[111])

def test_face_detector_on_image(img, face_detector):
    # convert BGR image to grayscale
    gray = convertToRGB(img)

    # find faces in image
    faces = face_detector.detectMultiScale(gray)

    # print number of faces detected in the image
    print('Number of faces detected:', len(faces))

    # get bounding box for each detected face
    for (x,y,w,h) in faces:
        # add bounding box to color image
        cv2.rectangle(img,(x,y-4),(x+w+4,y+h),(0,0,255),2)

    # convert BGR image to RGB for plotting
    cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

    # display the image, along with bounding box
    plt.imshow(cv_rgb)
    plt.show()

test_face_detector_on_image(img, haar_face_cascade)
Number of faces detected: 1
In [76]:
def convertToRGB(img): 
    return cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
In [77]:
# returns "True" if face is detected in image stored at img_path
def haar_face_detector(img_path):
    img = cv2.imread(img_path)
    gray = convertToRGB(img)
    faces = haar_face_cascade.detectMultiScale(gray)
    return len(faces) > 0
In [78]:
### TODO: Write your algorithm.
### Feel free to use as many code cells as needed.

def run_app(img_path):
    # check for human faces:
    if (haar_face_detector(img_path)):
        print("Hello Human!")
        predicted_breed = predict_breed_transfer(img_path)
        display_image(img_path, title=f"Predicted:{predicted_breed}")
        
        print("You look like a ...")
        print(predicted_breed.upper())
    # check if image has dogs:
    elif dog_detector(img_path):
        print("Hello Doggie!")
        predicted_breed = predict_breed_transfer(img_path)
        display_image(img_path, title=f"Predicted:{predicted_breed}")
        
        print("Your breed is most likley ...")
        print(predicted_breed.upper())
    else:
        print("Oh, we're sorry! We couldn't detect any dog or human face in the image.")
        display_image(img_path, title="...")
        print("Try another!")
    print("\n")

Step 6: Test Your Algorithm

In this section, you will take your new algorithm for a spin! What kind of dog does the algorithm think that you look like? If you have a dog, does it predict your dog's breed accurately? If you have a cat, does it mistakenly think that your cat is a dog?

(IMPLEMENTATION) Test Your Algorithm on Sample Images!

Test your algorithm at least six images on your computer. Feel free to use any images you like. Use at least two human and two dog images.

Question 6: Is the output better than you expected :) ? Or worse :( ? Provide at least three possible points of improvement for your algorithm.

Answer: (Three possible points for improvement)

Some improvements:

Fine tune the model to give a better accuracy

Return the top N predicted classes and their probabilities, not just one class

Hyper-parameter tunings: weight initializings, learning rates, drop-outs, batch_sizes, and optimizers will be helpful to improve performances.

In [85]:
## TODO: Execute your algorithm from Step 6 on
## at least 6 images on your computer.
## Feel free to use as many code cells as needed.

## suggested code, below
for file in np.hstack((human_files[:5], dog_files[:5])):
    run_app(file)
Hello Human!
You look like a ...
IRISH WOLFHOUND


Hello Human!
You look like a ...
DOBERMAN PINSCHER


Hello Human!
You look like a ...
AMERICAN WATER SPANIEL


Hello Human!
You look like a ...
BEAGLE


Hello Human!
You look like a ...
BLACK RUSSIAN TERRIER


Hello Doggie!
Your breed is most likley ...
MASTIFF


Hello Doggie!
Your breed is most likley ...
MASTIFF


Hello Doggie!
Your breed is most likley ...
BULLMASTIFF


Oh, we're sorry! We couldn't detect any dog or human face in the image.
Try another!


Hello Doggie!
Your breed is most likley ...
MASTIFF


In [84]:
dog_dir = "/data/dog_images/train/005.Alaskan_malamute"
nova_scotia_retriever_sample = os.path.join(dog_dir, random.choice(os.listdir(dog_dir)))
print(nova_scotia_retriever_sample)
display_image(nova_scotia_retriever_sample)
/data/dog_images/train/005.Alaskan_malamute/Alaskan_malamute_00332.jpg
In [ ]: